Upload Date | October 23 2021 02:50 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 10 |
Model | samsung SM-N960N |
Model ID | samsung SM-N960N |
Motherboard | exynos9810 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 2 revision 0 |
Base Frequency | 1.79 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 4 Cores @ 2.70 GHz |
Memory Information | |
---|---|
Size | 7.45 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
383
41.1 IPS |
|
Image Classification (F16)
|
100% |
634
68.0 IPS |
|
Image Classification (I8)
|
81% |
585
62.6 IPS |
|
Image Segmentation (F32)
|
100% |
779
4.81 IPS |
|
Image Segmentation (F16)
|
100% |
1758
10.9 IPS |
|
Image Segmentation (I8)
|
89% |
1685
10.4 IPS |
|
Pose Estimation (F32)
|
100% |
175
0.71 IPS |
|
Pose Estimation (F16)
|
0% |
604
2.44 IPS |
|
Pose Estimation (I8)
|
0% |
606
2.45 IPS |
|
Object Detection (F32)
|
100% |
170
5.97 IPS |
|
Object Detection (F16)
|
99% |
283
9.95 IPS |
|
Object Detection (I8)
|
54% |
238
8.36 IPS |
|
Face Detection (F32)
|
100% |
738
8.48 IPS |
|
Face Detection (F16)
|
97% |
1446
16.6 IPS |
|
Face Detection (I8)
|
75% |
1240
14.2 IPS |
|
Text Classification (F32)
|
100% |
314
124.2 IPS |
|
Text Classification (F16)
|
98% |
436
172.4 IPS |
|
Machine Translation (F32)
|
100% |
231
35.6 IPS |
|
Machine Translation (F16)
|
100% |
227
35.0 IPS |